<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
skillsBERT_v2_tf_epoch50
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0719
- Validation Loss: 6.8695
- Epoch: 49
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamW', 'weight_decay': 0.004, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
6.9371 | 7.0394 | 0 |
6.2533 | 6.4021 | 1 |
5.3659 | 5.4458 | 2 |
4.6461 | 5.1474 | 3 |
4.1548 | 4.8846 | 4 |
3.7971 | 4.8365 | 5 |
3.4967 | 4.8230 | 6 |
3.2181 | 4.7250 | 7 |
2.9618 | 4.7563 | 8 |
2.7063 | 4.7626 | 9 |
2.4568 | 4.7971 | 10 |
2.2107 | 4.8674 | 11 |
1.9720 | 4.9420 | 12 |
1.7525 | 5.0023 | 13 |
1.5379 | 5.0225 | 14 |
1.3392 | 5.1210 | 15 |
1.1577 | 5.3786 | 16 |
0.9902 | 5.4268 | 17 |
0.8440 | 5.4760 | 18 |
0.7105 | 5.5502 | 19 |
0.5960 | 5.6959 | 20 |
0.4975 | 5.7828 | 21 |
0.4183 | 5.9094 | 22 |
0.3559 | 5.9433 | 23 |
0.3040 | 5.9871 | 24 |
0.2589 | 6.0707 | 25 |
0.2325 | 6.1771 | 26 |
0.2039 | 6.4244 | 27 |
0.1821 | 6.8064 | 28 |
0.1684 | 6.4322 | 29 |
0.1562 | 6.4103 | 30 |
0.1452 | 6.5123 | 31 |
0.1375 | 6.5841 | 32 |
0.1279 | 6.4424 | 33 |
0.1222 | 6.7928 | 34 |
0.1135 | 6.7001 | 35 |
0.1123 | 6.7584 | 36 |
0.1039 | 6.7425 | 37 |
0.1003 | 6.7665 | 38 |
0.0997 | 6.7972 | 39 |
0.0939 | 6.7379 | 40 |
0.0934 | 6.8585 | 41 |
0.0874 | 6.9250 | 42 |
0.0861 | 7.0405 | 43 |
0.0833 | 7.3141 | 44 |
0.0819 | 7.1149 | 45 |
0.0789 | 7.0914 | 46 |
0.0783 | 6.9386 | 47 |
0.0761 | 7.2007 | 48 |
0.0719 | 6.8695 | 49 |
Framework versions
- Transformers 4.28.0.dev0
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.2